Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2784 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 11.3199. Min Range: -11.3199
Max Act: 11.2574. Min Act: -0.1700
Data Index: 367095 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.3199. Min Range: -11.3199
Max Act: 11.3199. Min Act: -0.1700
Data Index: 3513167 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.3199. Min Range: -11.3199
Max Act: 10.9449. Min Act: -0.1700
Data Index: 4478512 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.3199. Min Range: -11.3199
Max Act: 10.8199. Min Act: -0.1700
Data Index: 8025914 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.3199. Min Range: -11.3199
Max Act: 10.9449. Min Act: -0.1700
Data Index: 6937044 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.3199. Min Range: -11.3199
Max Act: 10.7574. Min Act: -0.1700
Data Index: 8420930 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.3199. Min Range: -11.3199
Max Act: 10.6949. Min Act: -0.1700
Data Index: 1199618 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.3199. Min Range: -11.3199
Max Act: 10.6949. Min Act: -0.1700
Data Index: 1044233 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.3199. Min Range: -11.3199
Max Act: 10.6949. Min Act: -0.1700
Data Index: 1083032 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.3199. Min Range: -11.3199
Max Act: 10.6324. Min Act: -0.1700
Data Index: 6102402 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.3199. Min Range: -11.3199
Max Act: 10.6324. Min Act: -0.1700
Data Index: 724309 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.3199. Min Range: -11.3199
Max Act: 10.5699. Min Act: -0.1700
Data Index: 4380311 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.3199. Min Range: -11.3199
Max Act: 10.6324. Min Act: -0.1700
Data Index: 888776 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.3199. Min Range: -11.3199
Max Act: 10.5699. Min Act: -0.1700
Data Index: 1475761 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.3199. Min Range: -11.3199
Max Act: 10.5699. Min Act: -0.1700
Data Index: 8015655 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.3199. Min Range: -11.3199
Max Act: 10.6324. Min Act: -0.1700
Data Index: 978777 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.3199. Min Range: -11.3199
Max Act: 10.4449. Min Act: -0.1700
Data Index: 4732012 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.3199. Min Range: -11.3199
Max Act: 10.5074. Min Act: -0.1700
Data Index: 4338282 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.3199. Min Range: -11.3199
Max Act: 10.4449. Min Act: -0.1700
Data Index: 1537141 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.3199. Min Range: -11.3199
Max Act: 10.3824. Min Act: -0.1700
Data Index: 3117843 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19